YOLOv8-16bit/ultralytics/yolo/utils/plotting.py

from pathlib import Path
from urllib.error import URLError

import cv2
import numpy as np
import torch
from PIL import Image, ImageDraw, ImageFont

from ultralytics.yolo.utils import FONT, USER_CONFIG_DIR

from .checks import check_font, check_requirements, is_ascii
from .files import increment_path
from .ops import clip_coords, scale_image, xywh2xyxy, xyxy2xywh


class Colors:
    # Ultralytics color palette https://ultralytics.com/
    def __init__(self):
        # hex = matplotlib.colors.TABLEAU_COLORS.values()
        hexs = ('FF3838', 'FF9D97', 'FF701F', 'FFB21D', 'CFD231', '48F90A', '92CC17', '3DDB86', '1A9334', '00D4BB',
                '2C99A8', '00C2FF', '344593', '6473FF', '0018EC', '8438FF', '520085', 'CB38FF', 'FF95C8', 'FF37C7')
        self.palette = [self.hex2rgb(f'#{c}') for c in hexs]
        self.n = len(self.palette)

    def __call__(self, i, bgr=False):
        c = self.palette[int(i) % self.n]
        return (c[2], c[1], c[0]) if bgr else c

    @staticmethod
    def hex2rgb(h):  # rgb order (PIL)
        return tuple(int(h[1 + i:1 + i + 2], 16) for i in (0, 2, 4))


colors = Colors()  # create instance for 'from utils.plots import colors'


class Annotator:
    # YOLOv5 Annotator for train/val mosaics and jpgs and detect/hub inference annotations
    def __init__(self, im, line_width=None, font_size=None, font='Arial.ttf', pil=False, example='abc'):
        assert im.data.contiguous, 'Image not contiguous. Apply np.ascontiguousarray(im) to Annotator() input images.'
        non_ascii = not is_ascii(example)  # non-latin labels, i.e. asian, arabic, cyrillic
        self.pil = pil or non_ascii
        if self.pil:  # use PIL
            self.im = im if isinstance(im, Image.Image) else Image.fromarray(im)
            self.draw = ImageDraw.Draw(self.im)
            self.font = check_pil_font(font='Arial.Unicode.ttf' if non_ascii else font,
                                       size=font_size or max(round(sum(self.im.size) / 2 * 0.035), 12))
        else:  # use cv2
            self.im = im
        self.lw = line_width or max(round(sum(im.shape) / 2 * 0.003), 2)  # line width

    def box_label(self, box, label='', color=(128, 128, 128), txt_color=(255, 255, 255)):
        # Add one xyxy box to image with label
        if self.pil or not is_ascii(label):
            self.draw.rectangle(box, width=self.lw, outline=color)  # box
            if label:
                w, h = self.font.getsize(label)  # text width, height
                outside = box[1] - h >= 0  # label fits outside box
                self.draw.rectangle(
                    (box[0], box[1] - h if outside else box[1], box[0] + w + 1,
                     box[1] + 1 if outside else box[1] + h + 1),
                    fill=color,
                )
                # self.draw.text((box[0], box[1]), label, fill=txt_color, font=self.font, anchor='ls')  # for PIL>8.0
                self.draw.text((box[0], box[1] - h if outside else box[1]), label, fill=txt_color, font=self.font)
        else:  # cv2
            p1, p2 = (int(box[0]), int(box[1])), (int(box[2]), int(box[3]))
            cv2.rectangle(self.im, p1, p2, color, thickness=self.lw, lineType=cv2.LINE_AA)
            if label:
                tf = max(self.lw - 1, 1)  # font thickness
                w, h = cv2.getTextSize(label, 0, fontScale=self.lw / 3, thickness=tf)[0]  # text width, height
                outside = p1[1] - h >= 3
                p2 = p1[0] + w, p1[1] - h - 3 if outside else p1[1] + h + 3
                cv2.rectangle(self.im, p1, p2, color, -1, cv2.LINE_AA)  # filled
                cv2.putText(self.im,
                            label, (p1[0], p1[1] - 2 if outside else p1[1] + h + 2),
                            0,
                            self.lw / 3,
                            txt_color,
                            thickness=tf,
                            lineType=cv2.LINE_AA)

    def masks(self, masks, colors, im_gpu=None, alpha=0.5):
        """Plot masks at once.
        Args:
            masks (tensor): predicted masks on cuda, shape: [n, h, w]
            colors (List[List[Int]]): colors for predicted masks, [[r, g, b] * n]
            im_gpu (tensor): img is in cuda, shape: [3, h, w], range: [0, 1]
            alpha (float): mask transparency: 0.0 fully transparent, 1.0 opaque
        """
        if self.pil:
            # convert to numpy first
            self.im = np.asarray(self.im).copy()
        if im_gpu is None:
            # Add multiple masks of shape(h,w,n) with colors list([r,g,b], [r,g,b], ...)
            if len(masks) == 0:
                return
            if isinstance(masks, torch.Tensor):
                masks = torch.as_tensor(masks, dtype=torch.uint8)
                masks = masks.permute(1, 2, 0).contiguous()
                masks = masks.cpu().numpy()
            # masks = np.ascontiguousarray(masks.transpose(1, 2, 0))
            masks = scale_image(masks.shape[:2], masks, self.im.shape)
            masks = np.asarray(masks, dtype=np.float32)
            colors = np.asarray(colors, dtype=np.float32)  # shape(n,3)
            s = masks.sum(2, keepdims=True).clip(0, 1)  # add all masks together
            masks = (masks @ colors).clip(0, 255)  # (h,w,n) @ (n,3) = (h,w,3)
            self.im[:] = masks * alpha + self.im * (1 - s * alpha)
        else:
            if len(masks) == 0:
                self.im[:] = im_gpu.permute(1, 2, 0).contiguous().cpu().numpy() * 255
            colors = torch.tensor(colors, device=im_gpu.device, dtype=torch.float32) / 255.0
            colors = colors[:, None, None]  # shape(n,1,1,3)
            masks = masks.unsqueeze(3)  # shape(n,h,w,1)
            masks_color = masks * (colors * alpha)  # shape(n,h,w,3)

            inv_alph_masks = (1 - masks * alpha).cumprod(0)  # shape(n,h,w,1)
            mcs = (masks_color * inv_alph_masks).sum(0) * 2  # mask color summand shape(n,h,w,3)

            im_gpu = im_gpu.flip(dims=[0])  # flip channel
            im_gpu = im_gpu.permute(1, 2, 0).contiguous()  # shape(h,w,3)
            im_gpu = im_gpu * inv_alph_masks[-1] + mcs
            im_mask = (im_gpu * 255).byte().cpu().numpy()
            self.im[:] = scale_image(im_gpu.shape, im_mask, self.im.shape)
        if self.pil:
            # convert im back to PIL and update draw
            self.fromarray(self.im)

    def rectangle(self, xy, fill=None, outline=None, width=1):
        # Add rectangle to image (PIL-only)
        self.draw.rectangle(xy, fill, outline, width)

    def text(self, xy, text, txt_color=(255, 255, 255), anchor='top'):
        # Add text to image (PIL-only)
        if anchor == 'bottom':  # start y from font bottom
            w, h = self.font.getsize(text)  # text width, height
            xy[1] += 1 - h
        self.draw.text(xy, text, fill=txt_color, font=self.font)

    def fromarray(self, im):
        # Update self.im from a numpy array
        self.im = im if isinstance(im, Image.Image) else Image.fromarray(im)
        self.draw = ImageDraw.Draw(self.im)

    def result(self):
        # Return annotated image as array
        return np.asarray(self.im)


def check_pil_font(font=FONT, size=10):
    # Return a PIL TrueType Font, downloading to CONFIG_DIR if necessary
    font = Path(font)
    font = font if font.exists() else (USER_CONFIG_DIR / font.name)
    try:
        return ImageFont.truetype(str(font) if font.exists() else font.name, size)
    except Exception:  # download if missing
        try:
            check_font(font)
            return ImageFont.truetype(str(font), size)
        except TypeError:
            check_requirements('Pillow>=8.4.0')  # known issue https://github.com/ultralytics/yolov5/issues/5374
        except URLError:  # not online
            return ImageFont.load_default()


def save_one_box(xyxy, im, file=Path('im.jpg'), gain=1.02, pad=10, square=False, BGR=False, save=True):
    # Save image crop as {file} with crop size multiple {gain} and {pad} pixels. Save and/or return crop
    xyxy = torch.tensor(xyxy).view(-1, 4)
    b = xyxy2xywh(xyxy)  # boxes
    if square:
        b[:, 2:] = b[:, 2:].max(1)[0].unsqueeze(1)  # attempt rectangle to square
    b[:, 2:] = b[:, 2:] * gain + pad  # box wh * gain + pad
    xyxy = xywh2xyxy(b).long()
    clip_coords(xyxy, im.shape)
    crop = im[int(xyxy[0, 1]):int(xyxy[0, 3]), int(xyxy[0, 0]):int(xyxy[0, 2]), ::(1 if BGR else -1)]
    if save:
        file.parent.mkdir(parents=True, exist_ok=True)  # make directory
        f = str(increment_path(file).with_suffix('.jpg'))
        # cv2.imwrite(f, crop)  # save BGR, https://github.com/ultralytics/yolov5/issues/7007 chroma subsampling issue
        Image.fromarray(crop[..., ::-1]).save(f, quality=95, subsampling=0)  # save RGB
    return crop